59 citations · 291 across the 45 of their papers we have counts for
8 papers · 1 filter
Reinforcement Learning by Guided Safe Exploration
Qisong Yang, Thiago D. Simão, Nils Jansen +2
Safety is critical to broadening the application of reinforcement learning (RL). Often, we train RL agents in a controlled environment, such as a laboratory, before deploying them…
More for Less: Safe Policy Improvement With Stronger Performance Guarantees
Patrick Wienhöft, Marnix Suilen, Thiago D. Simão +3
In an offline reinforcement learning setting, the safe policy improvement (SPI) problem aims to improve the performance of a behavior policy according to which sample data has been…
Efficient Sensitivity Analysis for Parametric Robust Markov Chains
Thom Badings, Sebastian Junges, Ahmadreza Marandi +2
We provide a novel method for sensitivity analysis of parametric robust Markov chains. These models incorporate parameters and sets of probability distributions to alleviate the of…
Act-Then-Measure: Reinforcement Learning for Partially Observable Environments with Active Measuring
Merlijn Krale, Thiago D. Simão, Nils Jansen
We study Markov decision processes (MDPs), where agents have direct control over when and how they gather information, as formalized by action-contingent noiselessly observable MDP…
Decision-Making Under Uncertainty: Beyond Probabilities
Thom Badings, Thiago D. Simão, Marnix Suilen +1
This position paper reflects on the state-of-the-art in decision-making under uncertainty. A classical assumption is that probabilities can sufficiently capture all uncertainty in…
Safe Policy Improvement for POMDPs via Finite-State Controllers
Thiago D. Simão, Marnix Suilen, Nils Jansen
We study safe policy improvement (SPI) for partially observable Markov decision processes (POMDPs). SPI is an offline reinforcement learning (RL) problem that assumes access to (1)…
Robust Control for Dynamical Systems With Non-Gaussian Noise via Formal Abstractions
Thom Badings, Licio Romao, Alessandro Abate +4
Controllers for dynamical systems that operate in safety-critical settings must account for stochastic disturbances. Such disturbances are often modeled as process noise in a dynam…
Robust Almost-Sure Reachability in Multi-Environment MDPs
Marck van der Vegt, Nils Jansen, Sebastian Junges
Multiple-environment MDPs (MEMDPs) capture finite sets of MDPs that share the states but differ in the transition dynamics. These models form a proper subclass of partially observa…